Need help in getting this to work for speeding up an application where my Object detection speedup pipeline is resulting in error.

Anyone who could help me fix this, please review the below error

Caused by op u’model_0/TRTEngineOp_20', defined at:
File “main.py”, line 2111, in <module>
forward(config)
File “main.py”, line 1357, in forward
models.append(get_model(config, i, controller=config.controller))
File “/home/aps/workdir/obj_detect/Object_Detection_Tracking/models.py”, line 61, in get_model
model = Mask_RCNN_FPN_frozen(config.load_from, gpuid)
File “/home/aps/workdir/obj_detect/Object_Detection_Tracking/models.py”, line 148, in __init__
name=self.var_prefix
File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/util/deprecation.py”, line 507, in new_func
return func(*args, **kwargs)
File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/importer.py”, line 442, in import_graph_def
_ProcessNewOps(graph)
File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/importer.py”, line 235, in _ProcessNewOps
for new_op in graph._add_new_tf_operations(compute_devices=False): # pylint: disable=protected-access
File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py”, line 3433, in _add_new_tf_operations
for c_op in c_api_util.new_tf_operations(self)
File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py”, line 3325, in _create_op_from_tf_operation
ret = Operation(c_op, self)
File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py”, line 1801, in __init__
self._traceback = tf_stack.extract_stack()

InternalError (see above for traceback): Native FunctionDef TRTEngineOp_20_native_segment can’t be found in function library
[[node model_0/TRTEngineOp_20 (defined at /home/aps/workdir/obj_detect/Object_Detection_Tracking/models.py:148) ]]
[[node model_0/final_boxes (defined at /home/aps/workdir/obj_detect/Object_Detection_Tracking/models.py:148) ]]